Back to skill

Security audit

hubei-exam-author

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because the reported activity is aligned with generating exam practice questions, with one low-severity concern about an overly broad activation trigger.

The verdict is benign with medium confidence, but the scan was partial: a local path-like reference in SKILL.md did not match a bundled artifact. Consider whether the possible unintended activation matters for your use, and review that unresolved reference before installing if you need fuller assurance.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
70% confidence
Finding

Overly Broad Trigger: description clause '按湖北省2026年技能高考计算机类考纲生成练习题,输出带知识点编号的题目JSON。Use when the user asks to 出题、生成题目、写练习题、模拟题 for 湖北技能高考 or Hubei CS skill exam' activates on 'to', which is too short and may match unintended inputs

Content

No source excerpt is available for this finding.